*BSD News Article 83456


Return to BSD News archive

Path: euryale.cc.adfa.oz.au!newshost.carno.net.au!harbinger.cc.monash.edu.au!munnari.OZ.AU!news.mel.connect.com.au!news.syd.connect.com.au!news.bri.connect.com.au!fjholden.OntheNet.com.au!news
From: Tony Griffiths <tonyg@OntheNet.com.au>
Newsgroups: comp.unix.bsd.freebsd.misc
Subject: Re: Can geometry affect D. I/O performance?
Date: Sat, 23 Nov 1996 12:32:51 +1000
Organization: On the Net (ISP on the Gold Coast, Australia)
Lines: 32
Message-ID: <32966253.791C@OntheNet.com.au>
References: <32913A95.17DE@csn.org>
Reply-To: tonyg@OntheNet.com.au
NNTP-Posting-Host: swanee.nt.com.au
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mailer: Mozilla 3.0 (WinNT; I)
To: mlb@csn.org

mlb@csn.org wrote:
> 
> hello.
> 
>    While the probe at boot correctly identifies the geometry of
>    my IDE drive ( the correct # of clys, hd's etc ), during
>    installation I configured with all 0's [zeros].
> 
>    My drive I/O seems a bit slow compared to my experiances
>    w/other Intel UNIX's, could my geometry ( or lack there of! )
>    be causing this?
> 
You might want to try rebuilding the kernel with the following extra
'option' -

controller	wda0	<blah blah> flags 0x80ff80ff intr wdaintr
				    ^^^^^^^^^^^^^^^^
to enable multi-block transfer!

>    Are there any obvious/ or frequntly tweaked kernel parameters
>    or buffers that I should adjust ( beyond the default )?
>
Not really...  memory is organised such that programs and buffer cache
both contend for available pages.  Anything not being used by programs
will be swallowed by the buffer cache if it want it!
 
>    thx in advance for any tips,
> 
>    Michael Borowski
>    mlb@csn.org

Tony